# Specular Lighting Causing Systematic Stereo Depth Bias / Drift

**URL:** <https://community.stereolabs.com/t/specular-lighting-causing-systematic-stereo-depth-bias-drift/10371>\
**Category:** C++\
**Tags:** multi-camera, sdk, ros, jetson, depth\
**Created:** [November 20, 2025, 8:54am UTC](https://community.stereolabs.com/t/specular-lighting-causing-systematic-stereo-depth-bias-drift/10371 "2025-11-20T08:54:24Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![mohamedsamirx](https://community.stereolabs.com/user_avatar/community.stereolabs.com/mohamedsamirx/32/5428_2.png) [@mohamedsamirx](https://community.stereolabs.com/u/mohamedsamirx)\
**Post date:** [November 20, 2025, 8:54am UTC](https://community.stereolabs.com/t/specular-lighting-causing-systematic-stereo-depth-bias-drift/10371/1 "2025-11-20T08:54:24Z")

</div>

I am using **two ZED X cameras** in a dual-stereo outdoor setup. Both sensors are fully calibrated, and I am running **Neural Depth mode**.

In deployments, I encounter major issues under **strong sunlight** (morning harsh reflections) and also when using a **flashlight** at night. Our target surface is **highly reflective** , which appears to severely degrade depth estimation.

The resulting problems:

- One camera produces a **systematically shifted** point cloud (depth bias), while the other remains aligned → **registration between the two fails**

- The degraded depth contains **heavy noise artifacts**

- Large **holes and invalid disparity** appear in specular regions

- The shift persists frame-to-frame, indicating **biased disparity** , not random noise

Calibration appears correct because the same setup performs well with controlled lighting.

**Questions:**

1. Is this a known failure mode of Neural Depth on reflective surfaces under strong illumination?

2. Are there recommended mitigation techniques (e.g., reduced exposure, depth mode changes, polarization filters, confidence-based masking)?

3. Any SDK settings to enforce more stability/consistency between the two stereo point clouds?

Any guidance would be greatly appreciated. I can provide images/logs if needed.

---

<div class="post-metadata">

**Author:** ![Myzhar](https://community.stereolabs.com/user_avatar/community.stereolabs.com/myzhar/32/11_2.png) [@Myzhar](https://community.stereolabs.com/u/Myzhar)\
**Post date:** [November 21, 2025, 2:14pm UTC](https://community.stereolabs.com/t/specular-lighting-causing-systematic-stereo-depth-bias-drift/10371/2 "2025-11-21T14:14:04Z")

</div>

Hi @mohamedsamirx  
Welcome to the [Stereolabs](https://www.stereolabs.com/) community.

> [@mohamedsamirx](#):
>
> In deployments, I encounter major issues under **strong sunlight** (morning harsh reflections) and also when using a **flashlight** at night. Our target surface is **highly reflective** , which appears to severely degrade depth estimation.

Do you have pictures showing the problem?

> [@mohamedsamirx](#):
>
> Is this a known failure mode of Neural Depth on reflective surfaces under strong illumination?

Specific challenging conditions can cause what you described.

> [@mohamedsamirx](#):
>
> Are there recommended mitigation techniques (e.g., reduced exposure, depth mode changes, polarization filters, confidence-based masking)?

You can try to tune the depth confidence value and enable the `remove_saturated_areas` run time parameter: [RuntimeParameters Struct Reference | API Reference | Stereolabs](https://www.stereolabs.com/docs/api/structsl_1_1RuntimeParameters.html#ad6ab99284d7835d6278981cebd7a0725)
